SOTAVerified

Multi-Armed Bandits

Multi-armed bandits refer to a task where a fixed amount of resources must be allocated between competing resources that maximizes expected gain. Typically these problems involve an exploration/exploitation trade-off.

( Image credit: Microsoft Research )

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 851–860 of 1262 papers

TitleStatusHype
Risk-Aware Algorithms for Adversarial Contextual Bandits—0
Risk-aware linear bandits with convex loss—0
Concentration bounds for CVaR estimation: The cases of light-tailed and heavy-tailed distributions—0
Robust and Performance Incentivizing Algorithms for Multi-Armed Bandits with Strategic Agents—0
Robust Contextual Linear Bandits—0
Exploiting Heterogeneity in Robust Federated Best-Arm Identification—0
Robust Generalization of Quadratic Neural Networks via Function Identification—0
Robust Multi-Agent Multi-Armed Bandits—0
Robustness Guarantees for Mode Estimation with an Application to Bandits—0
Robust Pareto Set Identification with Contaminated Bandit Feedback—0
Show:102550
← PrevPage 86 of 127Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1NeuralLinear FullPosterior-MRCumulative regret1.92—Unverified
2Linear FullPosterior-MRCumulative regret1.82—Unverified